| Samsung AI Center’s Moscow research team have combined with Skolkovo Institute of Science and Technology to publish a new document that shows how terrifying new software can be used to create 3-dimensional talking heads. The images are created via still images. The software’s creations are nothing short of stunning and scary. It can take a regular, common image of anyone and produce what appears to be a video communication from that person. Of course, the implications of such technology are unsettling. This means rival governments will be capable of serving up a completely fake video of politicians. It also means countries such as the United States could leverage such technology for its own purposes.
Here’s a sample of the technology below.
The researchers published document can be found here. It claims that as little as one image is needed to create the life-like videos. Although, the software tends to work most accurately when given a series of images, rather than a single image. “Crucially, only a handful of photographs (as little as one) is needed to create a new model, whereas the model trained on 32 images achieves perfect realism and personalization score in our user study (for 224p static images).”
The good news is that these same researchers claim the software has difficulty creating accurate personalities. They claim “landmark adaption” would need to occur in order to achieve personality matches.
That said, personality matches may not be needed in every creation. And there is plenty of opportunities to sample thousands of clips of global politicians, including President Trump or any number of Democratic 2020 Presidential candidates.
Such software could change the results of elections, thrust societies into civil wars, and subvert activism.